Online qualitative abstraction of cardiovascular hemodynamics for post cardiac surgery decision support

This paper addresses methods for online temporal abstraction of hemodynamic data for the purpose of being integrated in a computer-based decision support system in relation to post cardiac surgery patients. Temporal abstraction mechanisms provide a means of pre-processing and converting the monitored numerical data into a machine useable qualitative form. The temporal abstraction algorithm described in this paper is based on fuzzy clustering concepts. Synthetic signals which mimic the physiological signals of interest and real hemodynamic data recorded from clinical studies were used to evaluate these algorithms. Furthermore a cardiac output monitoring set-up was used to test the effectiveness of the algorithms under conditions similar to those existing in a real-time clinical environment.